[tmz] Add support for articles (fixes #5477)

diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index e808f2734ee75c941e1ca5df991c95d9f6b9d19d..b376fd279b6c5242002626234b83c4bbdf856ef6 100644 (file)
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -543,7 +543,10 @@ from .thesixtyone import TheSixtyOneIE
 from .thisav import ThisAVIE
 from .tinypic import TinyPicIE
 from .tlc import TlcIE, TlcDeIE
-from .tmz import TMZIE
+from .tmz import (
+    TMZIE,
+    TMZArticleIE,
+)
 from .tnaflix import TNAFlixIE
 from .thvideo import (
     THVideoIE,

diff --git a/youtube_dl/extractor/tmz.py b/youtube_dl/extractor/tmz.py
index c5c6fdc51b19fce90d45298858ce345bc901307e..7dbe68b5c228ea6d3fa20d835a60ecf38b820816 100644 (file)
--- a/youtube_dl/extractor/tmz.py
+++ b/youtube_dl/extractor/tmz.py
@@ -30,3 +30,31 @@ class TMZIE(InfoExtractor):
             'description': self._og_search_description(webpage),
             'thumbnail': self._html_search_meta('ThumbURL', webpage),
         }
+
+
+class TMZArticleIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?tmz\.com/\d{4}/\d{2}/\d{2}/(?P<id>[^/]+)/?'
+    _TEST = {
+        'url': 'http://www.tmz.com/2015/04/19/bobby-brown-bobbi-kristina-awake-video-concert',
+        'md5': 'e482a414a38db73087450e3a6ce69d00',
+        'info_dict': {
+            'id': '0_6snoelag',
+            'ext': 'mp4',
+            'title': 'Bobby Brown Tells Crowd ... Bobbi Kristina is Awake',
+            'description': 'Bobby Brown stunned his audience during a concert Saturday night, when he told the crowd, "Bobbi is awake.  She\'s watching me."',
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+        embedded_video_info_str = self._html_search_regex(
+            r'tmzVideoEmbedV2\("([^)]+)"\);', webpage, 'embedded video info')
+
+        embedded_video_info = self._parse_json(
+            embedded_video_info_str, video_id,
+            transform_source=lambda s: s.replace('\\', ''))
+
+        return self.url_result(
+            'http://www.tmz.com/videos/%s/' % embedded_video_info['id'])